Literatura académica sobre el tema "Convolutive Neural Networks"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte las listas temáticas de artículos, libros, tesis, actas de conferencias y otras fuentes académicas sobre el tema "Convolutive Neural Networks".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Artículos de revistas sobre el tema "Convolutive Neural Networks"
1
KIREI, B. S., M. D. TOPA, I. MURESAN, I. HOMANA y N. TOMA. "Blind Source Separation for Convolutive Mixtures with Neural Networks". Advances in Electrical and Computer Engineering 11, n.º 1 (2011): 63–68. http://dx.doi.org/10.4316/aece.2011.01010.
Texto completo
2
Karhunen, J., A. Cichocki, W. Kasprzak y P. Pajunen. "On Neural Blind Separation with Noise Suppression and Redundancy Reduction". International Journal of Neural Systems 08, n.º 02 (abril de 1997): 219–37. http://dx.doi.org/10.1142/s0129065797000239.
Texto completoResumen
Noise is an unavoidable factor in real sensor signals. We study how additive and convolutive noise can be reduced or even eliminated in the blind source separation (BSS) problem. Particular attention is paid to cases in which the number of sensors is larger than the number of sources. We propose various methods and associated adaptive learning algorithms for such an extended BSS problem. Performance and validity of the proposed approaches are demonstrated by extensive computer simulations.
3
Duan, Yunlong, Ziyu Han y Zhening Tang. "A lightweight plant disease recognition network based on Resnet". Applied and Computational Engineering 5, n.º 1 (14 de junio de 2023): 583–92. http://dx.doi.org/10.54254/2755-2721/5/20230651.
Texto completoResumen
Identification of foliar diseases is very important for the cultivation of plants. If no diseases are found, the cultivation results may decline, resulting in serious losses of related industries. Most of the early automatic recognition methods of plant leaves are based on manual features and classifiers, and the recognition performance is often unable to meet the actual complex application scenarios. Thanks to the rapid development of convolutional neural networks, such as ResNet, the accuracy of plant disease identification based on deep learning has made a breakthrough. However, convolutive neural network tends to have too many parameters, large amount of calculation and slow training speed, which is difficult to be used in various small and medium-sized plant cultivation industries, especially in small edge computing devices deployed in the field. This paper designs a new lightweight Resnet network structure, namely Resnet-9. The number of network layers in traditional Resnet is reduced. Compared with other commonly used plant disease recognition methods, the accuracy of Resnet is guaranteed and the network is more lightweight. The parameter of this model occupies only 6.6M memory and achieves 99.23% accuracy on public datasets. Even in the other data sets, the accuracy was still 95.15%. The effectiveness of the method is verified by comparative experiment.
4
Tong, Lian, Lan Yang, Xuan Wang y Li Liu. "Self-aware face emotion accelerated recognition algorithm: a novel neural network acceleration algorithm of emotion recognition for international students". PeerJ Computer Science 9 (26 de septiembre de 2023): e1611. http://dx.doi.org/10.7717/peerj-cs.1611.
Texto completoResumen
With an increasing number of human-computer interaction application scenarios, researchers are looking for computers to recognize human emotions more accurately and efficiently. Such applications are desperately needed at universities, where people want to understand the students’ psychology in real time to avoid catastrophes. This research proposed a self-aware face emotion accelerated recognition algorithm (SFEARA) that improves the efficiency of convolutional neural networks (CNNs) in the recognition of facial emotions. SFEARA will recognize that critical and non-critical regions of input data perform high-precision computation and convolutive low-precision computation during the inference process, and finally combine the results, which can help us get the emotional recognition model for international students. Based on a comparison of experimental data, the SFEARA algorithm has 1.3× to 1.6× higher computational efficiency and 30% to 40% lower energy consumption than conventional CNNs in emotion recognition applications, is better suited to the real-time scenario with more background information.
5
Sineglazov, Victor y Petro Chynnyk. "Quantum Convolution Neural Network". Electronics and Control Systems 2, n.º 76 (23 de junio de 2023): 40–45. http://dx.doi.org/10.18372/1990-5548.76.17667.
Texto completoResumen
In this work, quantum convolutional neural networks are considered in the task of recognizing handwritten digits. A proprietary quantum scheme for the convolutional layer of a quantum convolutional neural network is proposed. A proprietary quantum scheme for the pooling layer of a quantum convolutional neural network is proposed. The results of learning quantum convolutional neural networks are analyzed. The built models were compared and the best one was selected based on the accuracy, recall, precision and f1-score metrics. A comparative analysis was made with the classic convolutional neural network based on accuracy, recall, precision and f1-score metrics. The object of the study is the task of recognizing numbers. The subject of research is convolutional neural network, quantum convolutional neural network. The result of this work can be applied in the further research of quantum computing in the tasks of artificial intelligence.
6
Lü Benyuan, 吕本远, 禚真福 Zhuo Zhenfu, 韩永赛 Han Yongsai y 张立朝 Zhang Lichao. "基于Faster区域卷积神经网络的目标检测". Laser & Optoelectronics Progress 58, n.º 22 (2021): 2210017. http://dx.doi.org/10.3788/lop202158.2210017.
Texto completo
7
Anmin, Kong y Zhao Bin. "A Parallel Loading Based Accelerator for Convolution Neural Network". International Journal of Machine Learning and Computing 10, n.º 5 (5 de octubre de 2020): 669–74. http://dx.doi.org/10.18178/ijmlc.2020.10.5.989.
Texto completo
8
Sharma, Himanshu y Rohit Agarwal. "Channel Enhanced Deep Convolution Neural Network based Cancer Classification". Journal of Advanced Research in Dynamical and Control Systems 11, n.º 10-SPECIAL ISSUE (31 de octubre de 2019): 610–17. http://dx.doi.org/10.5373/jardcs/v11sp10/20192849.
Texto completo
9
Anem, Smt Jayalaxmi, B. Dharani, K. Raveendra, CH Nikhil y K. Akhil. "Leveraging Convolution Neural Network (CNN) for Skin Cancer Identification". International Journal of Research Publication and Reviews 5, n.º 4 (abril de 2024): 2150–55. http://dx.doi.org/10.55248/gengpi.5.0424.0955.
Texto completo
10
Oh, Seokjin, Jiyong An y Kyeong-Sik Min. "Area-Efficient Mapping of Convolutional Neural Networks to Memristor Crossbars Using Sub-Image Partitioning". Micromachines 14, n.º 2 (25 de enero de 2023): 309. http://dx.doi.org/10.3390/mi14020309.
Texto completoResumen
Memristor crossbars can be very useful for realizing edge-intelligence hardware, because the neural networks implemented by memristor crossbars can save significantly more computing energy and layout area than the conventional CMOS (complementary metal–oxide–semiconductor) digital circuits. One of the important operations used in neural networks is convolution. For performing the convolution by memristor crossbars, the full image should be partitioned into several sub-images. By doing so, each sub-image convolution can be mapped to small-size unit crossbars, of which the size should be defined as 128 × 128 or 256 × 256 to avoid the line resistance problem caused from large-size crossbars. In this paper, various convolution schemes with 3D, 2D, and 1D kernels are analyzed and compared in terms of neural network’s performance and overlapping overhead. The neural network’s simulation indicates that the 2D + 1D kernels can perform the sub-image convolution using a much smaller number of unit crossbars with less rate loss than the 3D kernels. When the CIFAR-10 dataset is tested, the mapping of sub-image convolution of 2D + 1D kernels to crossbars shows that the number of unit crossbars can be reduced almost by 90% and 95%, respectively, for 128 × 128 and 256 × 256 crossbars, compared with the 3D kernels. On the contrary, the rate loss of 2D + 1D kernels can be less than 2%. To improve the neural network’s performance more, the 2D + 1D kernels can be combined with 3D kernels in one neural network. When the normalized ratio of 2D + 1D layers is around 0.5, the neural network’s performance indicates very little rate loss compared to when the normalized ratio of 2D + 1D layers is zero. However, the number of unit crossbars for the normalized ratio = 0.5 can be reduced by half compared with that for the normalized ratio = 0.
Tesis sobre el tema "Convolutive Neural Networks"
1
Heuillet, Alexandre. "Exploring deep neural network differentiable architecture design". Electronic Thesis or Diss., université Paris-Saclay, 2023. http://www.theses.fr/2023UPASG069.
Texto completoResumen
L'intelligence artificielle (IA) a gagné en popularité ces dernières années, principalement en raison de ses applications réussies dans divers domaines tels que l'analyse de données textuelles, la vision par ordinateur et le traitement audio. La résurgence des techniques d'apprentissage profond a joué un rôle central dans ce succès. L'article révolutionnaire de Krizhevsky et al., AlexNet, a réduit l'écart entre les performances humaines et celles des machines dans les tâches de classification d'images. Des articles ultérieurs tels que Xception et ResNet ont encore renforcé l'apprentissage profond en tant que technique de pointe, ouvrant de nouveaux horizons pour la communauté de l'IA. Le succès de l'apprentissage profond réside dans son architecture, conçue manuellement avec des connaissances d'experts et une validation empirique. Cependant, ces architectures n'ont pas la certitude d'être la solution optimale. Pour résoudre ce problème, des articles récents ont introduit le concept de Recherche d'Architecture Neuronale ( extit{NAS}), permettant l'automatisation de la conception des architectures profondes. Cependant, la majorités des approches initiales se sont concentrées sur de grandes architectures avec des objectifs spécifiques (par exemple, l'apprentissage supervisé) et ont utilisé des techniques d'optimisation coûteuses en calcul telles que l'apprentissage par renforcement et les algorithmes génétiques. Dans cette thèse, nous approfondissons cette idée en explorant la conception automatique d'architectures profondes, avec une emphase particulière sur les méthodes extit{NAS} différentiables ( extit{DNAS}), qui représentent la tendance actuelle en raison de leur efficacité computationnelle. Bien que notre principal objectif soit les réseaux convolutifs ( extit{CNNs}), nous explorons également les Vision Transformers (ViTs) dans le but de concevoir des architectures rentables adaptées aux applications en temps réelArtificial Intelligence (AI) has gained significant popularity in recent years, primarily due to its successful applications in various domains, including textual data analysis, computer vision, and audio processing. The resurgence of deep learning techniques has played a central role in this success. The groundbreaking paper by Krizhevsky et al., AlexNet, narrowed the gap between human and machine performance in image classification tasks. Subsequent papers such as Xception and ResNet have further solidified deep learning as a leading technique, opening new horizons for the AI community. The success of deep learning lies in its architecture, which is manually designed with expert knowledge and empirical validation. However, these architectures lack the certainty of an optimal solution. To address this issue, recent papers introduced the concept of Neural Architecture Search (NAS), enabling the learning of deep architectures. However, most initial approaches focused on large architectures with specific targets (e.g., supervised learning) and relied on computationally expensive optimization techniques such as reinforcement learning and evolutionary algorithms. In this thesis, we further investigate this idea by exploring automatic deep architecture design, with a particular emphasis on differentiable NAS (DNAS), which represents the current trend in NAS due to its computational efficiency. While our primary focus is on Convolutional Neural Networks (CNNs), we also explore Vision Transformers (ViTs) with the goal of designing cost-effective architectures suitable for real-time applications
2
Maragno, Alessandro. "Programmazione di Convolutional Neural Networks orientata all'accelerazione su FPGA". Master's thesis, Alma Mater Studiorum - Università di Bologna, 2016. http://amslaurea.unibo.it/12476/.
Texto completoResumen
Attualmente la Computer Vision, disciplina che consente di estrarre informazioni a partire da immagini digitali, è uno dei settori informatici più in fermento. Grazie alle recenti conquiste e progressi, tale settore ha raggiunto uno stato di maturità tale da poter essere applicato in svariati ambiti, a partire da quello industriale, fino ad arrivare ad applicazioni più vicine alla vita quotidiana. In particolare, si è raggiunto uno stato dell'arte sempre più solido nel campo del riconoscimento di oggetti (object detection) grazie allo sviluppo delle Convolutional Neural Networks (CNN): sistemi che si basano su un modello matematico, che viene gradualmente raffinato in base all'esperienza stessa del sistema nell'esecuzione di questo task, acquisita mediante tecniche di machine learning. Grazie a ciò, le CNN sono in grado di riconoscere e classificare il contenuto di immagini, dando loro una semantica. Tali sistemi però richiedono una grande capacità computazionale ed un'ingente quantità di memoria, pertanto la loro esecuzione avviene maggiormente su architetture potenti, come le GPU. Nonostante ciò, una delle sfide attualmente più importanti riguarda la classificazione in tempo reale di immagini eseguendo le reti neurali convolutive anche su architetture con disponibilità energetica e capacità computazionali ridotte, quali sono i sistemi embedded. Quindi, nel seguente trattato si propone un'implementazione di CNN riconfigurabile realizzata in linguaggio C. Ciò è risultato in un sistema semplice e modulare che con diverse ottimizzazioni ad-hoc può essere considerato un buon candidato per il porting su architetture embedded riconfigurabili FPGA.
3
Abbasi, Mahdieh. "Toward robust deep neural networks". Doctoral thesis, Université Laval, 2020. http://hdl.handle.net/20.500.11794/67766.
Texto completoResumen
Dans cette thèse, notre objectif est de développer des modèles d’apprentissage robustes et fiables mais précis, en particulier les Convolutional Neural Network (CNN), en présence des exemples anomalies, comme des exemples adversaires et d’échantillons hors distribution –Out-of-Distribution (OOD). Comme la première contribution, nous proposons d’estimer la confiance calibrée pour les exemples adversaires en encourageant la diversité dans un ensemble des CNNs. À cette fin, nous concevons un ensemble de spécialistes diversifiés avec un mécanisme de vote simple et efficace en termes de calcul pour prédire les exemples adversaires avec une faible confiance tout en maintenant la confiance prédicative des échantillons propres élevée. En présence de désaccord dans notre ensemble, nous prouvons qu’une borne supérieure de 0:5 + _0 peut être établie pour la confiance, conduisant à un seuil de détection global fixe de tau = 0; 5. Nous justifions analytiquement le rôle de la diversité dans notre ensemble sur l’atténuation du risque des exemples adversaires à la fois en boîte noire et en boîte blanche. Enfin, nous évaluons empiriquement la robustesse de notre ensemble aux attaques de la boîte noire et de la boîte blanche sur plusieurs données standards. La deuxième contribution vise à aborder la détection d’échantillons OOD à travers un modèle de bout en bout entraîné sur un ensemble OOD approprié. À cette fin, nous abordons la question centrale suivante : comment différencier des différents ensembles de données OOD disponibles par rapport à une tâche de distribution donnée pour sélectionner la plus appropriée, ce qui induit à son tour un modèle calibré avec un taux de détection des ensembles inaperçus de données OOD? Pour répondre à cette question, nous proposons de différencier les ensembles OOD par leur niveau de "protection" des sub-manifolds. Pour mesurer le niveau de protection, nous concevons ensuite trois nouvelles mesures efficaces en termes de calcul à l’aide d’un CNN vanille préformé. Dans une vaste série d’expériences sur les tâches de classification d’image et d’audio, nous démontrons empiriquement la capacité d’un CNN augmenté (A-CNN) et d’un CNN explicitement calibré pour détecter une portion significativement plus grande des exemples OOD. Fait intéressant, nous observons également qu’un tel A-CNN (nommé A-CNN) peut également détecter les adversaires exemples FGS en boîte noire avec des perturbations significatives. En tant que troisième contribution, nous étudions de plus près de la capacité de l’A-CNN sur la détection de types plus larges d’adversaires boîte noire (pas seulement ceux de type FGS). Pour augmenter la capacité d’A-CNN à détecter un plus grand nombre d’adversaires,nous augmentons l’ensemble d’entraînement OOD avec des échantillons interpolés inter-classes. Ensuite, nous démontrons que l’A-CNN, entraîné sur tous ces données, a un taux de détection cohérent sur tous les types des adversaires exemples invisibles. Alors que la entraînement d’un A-CNN sur des adversaires PGD ne conduit pas à un taux de détection stable sur tous les types d’adversaires, en particulier les types inaperçus. Nous évaluons également visuellement l’espace des fonctionnalités et les limites de décision dans l’espace d’entrée d’un CNN vanille et de son homologue augmenté en présence d’adversaires et de ceux qui sont propres. Par un A-CNN correctement formé, nous visons à faire un pas vers un modèle d’apprentissage debout en bout unifié et fiable avec de faibles taux de risque sur les échantillons propres et les échantillons inhabituels, par exemple, les échantillons adversaires et OOD. La dernière contribution est de présenter une application de A-CNN pour l’entraînement d’un détecteur d’objet robuste sur un ensemble de données partiellement étiquetées, en particulier un ensemble de données fusionné. La fusion de divers ensembles de données provenant de contextes similaires mais avec différents ensembles d’objets d’intérêt (OoI) est un moyen peu coûteux de créer un ensemble de données à grande échelle qui couvre un plus large spectre d’OoI. De plus, la fusion d’ensembles de données permet de réaliser un détecteur d’objet unifié, au lieu d’en avoir plusieurs séparés, ce qui entraîne une réduction des coûts de calcul et de temps. Cependant, la fusion d’ensembles de données, en particulier à partir d’un contexte similaire, entraîne de nombreuses instances d’étiquetées manquantes. Dans le but d’entraîner un détecteur d’objet robuste intégré sur un ensemble de données partiellement étiquetées mais à grande échelle, nous proposons un cadre d’entraînement auto-supervisé pour surmonter le problème des instances d’étiquettes manquantes dans les ensembles des données fusionnés. Notre cadre est évalué sur un ensemble de données fusionné avec un taux élevé d’étiquettes manquantes. Les résultats empiriques confirment la viabilité de nos pseudo-étiquettes générées pour améliorer les performances de YOLO, en tant que détecteur d’objet à la pointe de la technologie.In this thesis, our goal is to develop robust and reliable yet accurate learning models, particularly Convolutional Neural Networks (CNNs), in the presence of adversarial examples and Out-of-Distribution (OOD) samples. As the first contribution, we propose to predict adversarial instances with high uncertainty through encouraging diversity in an ensemble of CNNs. To this end, we devise an ensemble of diverse specialists along with a simple and computationally efficient voting mechanism to predict the adversarial examples with low confidence while keeping the predictive confidence of the clean samples high. In the presence of high entropy in our ensemble, we prove that the predictive confidence can be upper-bounded, leading to have a globally fixed threshold over the predictive confidence for identifying adversaries. We analytically justify the role of diversity in our ensemble on mitigating the risk of both black-box and white-box adversarial examples. Finally, we empirically assess the robustness of our ensemble to the black-box and the white-box attacks on several benchmark datasets.The second contribution aims to address the detection of OOD samples through an end-to-end model trained on an appropriate OOD set. To this end, we address the following central question: how to differentiate many available OOD sets w.r.t. a given in distribution task to select the most appropriate one, which in turn induces a model with a high detection rate of unseen OOD sets? To answer this question, we hypothesize that the “protection” level of in-distribution sub-manifolds by each OOD set can be a good possible property to differentiate OOD sets. To measure the protection level, we then design three novel, simple, and cost-effective metrics using a pre-trained vanilla CNN. In an extensive series of experiments on image and audio classification tasks, we empirically demonstrate the abilityof an Augmented-CNN (A-CNN) and an explicitly-calibrated CNN for detecting a significantly larger portion of unseen OOD samples, if they are trained on the most protective OOD set. Interestingly, we also observe that the A-CNN trained on the most protective OOD set (calledA-CNN) can also detect the black-box Fast Gradient Sign (FGS) adversarial examples. As the third contribution, we investigate more closely the capacity of the A-CNN on the detection of wider types of black-box adversaries. To increase the capability of A-CNN to detect a larger number of adversaries, we augment its OOD training set with some inter-class interpolated samples. Then, we demonstrate that the A-CNN trained on the most protective OOD set along with the interpolated samples has a consistent detection rate on all types of unseen adversarial examples. Where as training an A-CNN on Projected Gradient Descent (PGD) adversaries does not lead to a stable detection rate on all types of adversaries, particularly the unseen types. We also visually assess the feature space and the decision boundaries in the input space of a vanilla CNN and its augmented counterpart in the presence of adversaries and the clean ones. By a properly trained A-CNN, we aim to take a step toward a unified and reliable end-to-end learning model with small risk rates on both clean samples and the unusual ones, e.g. adversarial and OOD samples.The last contribution is to show a use-case of A-CNN for training a robust object detector on a partially-labeled dataset, particularly a merged dataset. Merging various datasets from similar contexts but with different sets of Object of Interest (OoI) is an inexpensive way to craft a large-scale dataset which covers a larger spectrum of OoIs. Moreover, merging datasets allows achieving a unified object detector, instead of having several separate ones, resultingin the reduction of computational and time costs. However, merging datasets, especially from a similar context, causes many missing-label instances. With the goal of training an integrated robust object detector on a partially-labeled but large-scale dataset, we propose a self-supervised training framework to overcome the issue of missing-label instances in the merged datasets. Our framework is evaluated on a merged dataset with a high missing-label rate. The empirical results confirm the viability of our generated pseudo-labels to enhance the performance of YOLO, as the current (to date) state-of-the-art object detector.
4
Kapoor, Rishika. "Malaria Detection Using Deep Convolution Neural Network". University of Cincinnati / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1613749143868579.
Texto completo
5
Yu, Xiafei. "Wide Activated Separate 3D Convolution for Video Super-Resolution". Thesis, Université d'Ottawa / University of Ottawa, 2019. http://hdl.handle.net/10393/39974.
Texto completoResumen
Video super-resolution (VSR) aims to recover a realistic high-resolution (HR) frame
from its corresponding center low-resolution (LR) frame and several neighbouring supporting frames. The neighbouring supporting LR frames can provide extra information to help recover the HR frame. However, these frames are not aligned with the center frame due to the motion of objects. Recently, many video super-resolution methods based on deep learning have been proposed with the rapid development of neural networks. Most of these methods utilize motion estimation and compensation models as preprocessing to handle spatio-temporal alignment problem. Therefore, the accuracy of these motion estimation models are critical for predicting the high-resolution frames. Inaccurate results of motion compensation models will lead to artifacts and blurs, which also will damage the recovery of high-resolution frames. We propose an effective wide activated separate 3 dimensional (3D) Convolution Neural Network (CNN) for video super-resolution to overcome the drawback of utilizing motion compensation models. Separate 3D convolution factorizes the 3D convolution into convolutions in the spatial and temporal domain, which have benefit for the optimization of spatial and temporal convolution components. Therefore, our method can capture temporal and spatial information of input frames simultaneously without additional motion evaluation and compensation model. Moreover, the experimental results demonstrated the effectiveness of the proposed wide activated separate 3D CNN.
6
Messou, Ehounoud Joseph Christopher. "Handling Invalid Pixels in Convolutional Neural Networks". Thesis, Virginia Tech, 2020. http://hdl.handle.net/10919/98619.
Texto completoResumen
Most neural networks use a normal convolutional layer that assumes that all input pixels are valid pixels. However, pixels added to the input through padding result in adding extra information that was not initially present. This extra information can be considered invalid. Invalid pixels can also be inside the image where they are referred to as holes in completion tasks like image inpainting. In this work, we look for a method that can handle both types of invalid pixels. We compare on the same test bench two methods previously used to handle invalid pixels outside the image (Partial and Edge convolutions) and one method that was designed for invalid pixels inside the image (Gated convolution). We show that Partial convolution performs the best in image classification while Gated convolution has the advantage on semantic segmentation. As for hotel recognition with masked regions, none of the methods seem appropriate to generate embeddings that leverage the masked regions.Master of Science
A module at the heart of deep neural networks built for Artificial Intelligence is the convolutional layer. When multiple convolutional layers are used together with other modules, a Convolutional Neural Network (CNN) is obtained. These CNNs can be used for tasks such as image classification where they tell if the object in an image is a chair or a car, for example. Most CNNs use a normal convolutional layer that assumes that all parts of the image fed to the network are valid. However, most models zero pad the image at the beginning to maintain a certain output shape. Zero padding is equivalent to adding a black frame around the image. These added pixels result in adding information that was not initially present. Therefore, this extra information can be considered invalid. Invalid pixels can also be inside the image where they are referred to as holes in completion tasks like image inpainting where the network is asked to fill these holes and give a realistic image. In this work, we look for a method that can handle both types of invalid pixels. We compare on the same test bench two methods previously used to handle invalid pixels outside the image (Partial and Edge convolutions) and one method that was designed for invalid pixels inside the image (Gated convolution). We show that Partial convolution performs the best in image classification while Gated convolution has the advantage on semantic segmentation. As for hotel recognition with masked regions, none of the methods seem appropriate to generate embeddings that leverage the masked regions.
7
Ngo, Kalle. "FPGA Hardware Acceleration of Inception Style Parameter Reduced Convolution Neural Networks". Thesis, KTH, Skolan för informations- och kommunikationsteknik (ICT), 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-205026.
Texto completoResumen
Some researchers have noted that the growth rate in the number of network parameters of many recently proposed state-of-the-art CNN topologies is placing unrealistic demands on hardware resources and limits the practical applications of Neural Networks. This is particularly apparent when considering many of the projected applications (IoT, autonomous vehicles, etc) utilize embedded systems with even greater restrictions on computation and memory bandwidth than the typical research-class computer cluster that the CNN was designed on. The GoogLeNet CNN in 2014 proposed a new level of organization (“Inception Module”) that was demonstrated in competition to achieve similar/better performance, while using an order of magnitude less network parameters than the other competing topologies. This thesis explores the characteristics of the new GoogLeNet inception modules and the implications it presents to current CNN accelerator architectures. A custom FPGA accelerator is proposed to offset the inception module’s increased need to buffer large intermediate convolution arrays through array partitioning and cascading two convolution operations into a single pipeline pass. A Xilinx Artix-7 FPGA was used to implement architecture where it was able continuously supply data to the 331 utilized DSP blocks (approx. half of total available), while using only a quarter of the DDR bandwidth to achieve a peak throughput of 9.11 GFLOPS. The low utilization of the DDR bandwidth suggests that with some optimization, the design can be scaled up to better utilize the available resources and increase throughput.
8
Pappone, Francesco. "Graph neural networks: theory and applications". Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/23893/.
Texto completoResumen
Le reti neurali artificiali hanno visto, negli ultimi anni, una crescita vertiginosa nelle loro applicazioni e nelle architetture dei modelli impiegati. In questa tesi introduciamo le reti neurali su domini euclidei, in particolare mostrando l’importanza dell’equivarianza di traslazione nelle reti convoluzionali, e introduciamo, per analogia, un’estensione della convoluzione a dati strutturati come grafi. Inoltre presentiamo le architetture dei principali Graph Neural Network ed esponiamo, per ognuna delle tre architetture proposte (Spectral graph Convolutional Network, Graph Convolutional Network, Graph Attention neTwork) un’applicazione che ne mostri sia il funzionamento che l’importanza. Discutiamo, ulteriormente, l’implementazione di un algoritmo di classificazione basato su due varianti dell’architettura Graph Convolutional Network, addestrato e testato sul dataset PROTEINS, capace di classificare le proteine del dataset in due categorie: enzimi e non enzimi.
9
Sung, Wei-Hong. "Investigating minimal Convolution Neural Networks (CNNs) for realtime embedded eye feature detection". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-281338.
Texto completoResumen
With the rapid rise of neural networks, many tasks that used to be difficult to complete in traditional methods can now be solved well, especially in the computer vision field. However, as the tasks we have to solve have become more and more complex, the neural networks we use are becoming deeper and larger. Therefore, although some embedded systems are powerful nowadays, most embedded systems still suffer from memory and computation limitations, which means it is hard to deploy our large neural networks on these embedded devices. This project aims to explore different methods to compress the original large model. That is, we first train a baseline model, YOLOv3[1], which is a famous object detection network, and then we use two methods to compress the baseline model. The first method is pruning by using sparsity training, and we do channel pruning according to the scaling factor value after sparsity training. Based on the idea of this method, we have made three explorations. Firstly, we take the union mask strategy to solve the dimension problem of the shortcut-related layers in YOLOv3[1]. Secondly, we try to absorb the shifting factor information into subsequent layers. Finally, we implement the layer pruning and combine it with channel pruning. The second method is pruning by using Neural Architecture Search (NAS), which uses a deep reinforcement framework to automatically find the best compression ratio for each layer. At the end of this report, we analyze the key findings and conclusions of our experiment and purpose the future work which could potentially improve our project.Med den snabba ökningen av neurala nätverk kan många uppgifter som brukade vara svåra att utföra i traditionella metoder nu lösas bra, särskilt inom datorsynsfältet. Men eftersom uppgifterna vi måste lösa har blivit mer och mer komplexa, blir de neurala nätverken vi använder djupare och större. Därför, även om vissa inbäddade system är kraftfulla för närvarande, lider de flesta inbäddade system fortfarande av minnes- och beräkningsbegränsningar, vilket innebär att det är svårt att distribuera våra stora neurala nätverk på dessa inbäddade enheter. Projektet syftar till att utforska olika metoder för att komprimera den ursprungliga stora modellen. Det vill säga, vi tränar först en baslinjemodell, YOLOv3[1], som är ett berömt objektdetekteringsnätverk, och sedan använder vi två metoder för att komprimera basmodellen. Den första metoden är beskärning med hjälp av sparsity training, och vi kanalskärning enligt skalningsfaktorvärdet efter sparsity training. Baserat på idén om denna metod har vi gjort tre utforskningar. För det första tar vi unionens maskstrategi för att lösa dimensionsproblemet för genvägsrelaterade lager i YOLOv3[1]. För det andra försöker vi absorbera informationen om skiftande faktorer i efterföljande lager. Slutligen implementerar vi lagerskärningen och kombinerar det med kanalbeskärning. Den andra metoden är beskärning med NAS, som använder en djup förstärkningsram för att automatiskt hitta det bästa kompressionsförhållandet för varje lager. I slutet av denna rapport analyserar vi de viktigaste resultaten och slutsatserna i vårt experiment och syftar till det framtida arbetet som potentiellt kan förbättra vårt projekt.
10
Wu, Jindong. "Pooling strategies for graph convolution neural networks and their effect on classification". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-288953.
Texto completoResumen
With the development of graph neural networks, this novel neural network has been applied in a broader and broader range of fields. One of the thorny problems researchers face in this field is selecting suitable pooling methods for a specific research task from various existing pooling methods. In this work, based on the existing mainstream graph pooling methods, we develop a benchmark neural network framework that can be used to compare these different graph pooling methods. By using the framework, we compare four mainstream graph pooling methods and explore their characteristics. Furthermore, we expand two methods for explaining neural network decisions for convolution neural networks to graph neural networks and compare them with the existing GNNExplainer. We run experiments on standard graph classification tasks using the developed framework and discuss the different pooling methods’ distinctive characteristics. Furthermore, we verify the proposed extensions of the explanation methods’ correctness and measure the agreements among the produced explanations. Finally, we explore the characteristics of different methods for explaining neural network decisions and the insights of different pooling methods by applying these explanation methods.Med utvecklingen av grafneurala nätverk har detta nya neurala nätverk tillämpats i olika område. Ett av de svåra problemen för forskare inom detta område är hur man väljer en lämplig poolningsmetod för en specifik forskningsuppgift från en mängd befintliga poolningsmetoder. I den här arbetet, baserat på de befintliga vanliga grafpoolingsmetoderna, utvecklar vi ett riktmärke för neuralt nätverk ram som kan användas till olika diagram pooling metoders jämförelse. Genom att använda ramverket jämför vi fyra allmängiltig diagram pooling metod och utforska deras egenskaper. Dessutom utvidgar vi två metoder för att förklara beslut om neuralt nätverk från convolution neurala nätverk till diagram neurala nätverk och jämföra dem med befintliga GNNExplainer. Vi kör experiment av grafisk klassificering uppgifter under benchmarkingramverk och hittade olika egenskaper av olika diagram pooling metoder. Dessutom verifierar vi korrekthet i dessa förklarningsmetoder som vi utvecklade och mäter överenskommelserna mellan dem. Till slut, vi försöker utforska egenskaper av olika metoder för att förklara neuralt nätverks beslut och deras betydelse för att välja pooling metoder i grafisk neuralt nätverk.
Capítulos de libros sobre el tema "Convolutive Neural Networks"
1
Mei, Tiemin, Fuliang Yin, Jiangtao Xi y Joe F. Chicharo. "Cumulant-Based Blind Separation of Convolutive Mixtures". En Advances in Neural Networks – ISNN 2004, 672–77. Berlin, Heidelberg: Springer Berlin Heidelberg, 2004. http://dx.doi.org/10.1007/978-3-540-28647-9_110.
Texto completo
2
He, Zhaoshui, Shengli Xie y Yuli Fu. "FIR Convolutive BSS Based on Sparse Representation". En Advances in Neural Networks – ISNN 2005, 532–37. Berlin, Heidelberg: Springer Berlin Heidelberg, 2005. http://dx.doi.org/10.1007/11427445_87.
Texto completo
3
Zhang, Hua y Dazhang Feng. "Convolutive Blind Separation of Non-white Broadband Signals Based on a Double-Iteration Method". En Advances in Neural Networks - ISNN 2006, 1195–201. Berlin, Heidelberg: Springer Berlin Heidelberg, 2006. http://dx.doi.org/10.1007/11759966_177.
Texto completo
4
Mei, Tiemin, Jiangtao Xi, Fuliang Yin y Joe F. Chicharo. "Joint Diagonalization of Power Spectral Density Matrices for Blind Source Separation of Convolutive Mixtures". En Advances in Neural Networks – ISNN 2005, 520–25. Berlin, Heidelberg: Springer Berlin Heidelberg, 2005. http://dx.doi.org/10.1007/11427445_85.
Texto completo
5
Peng, Chunyi, Xianda Zhang y Qutang Cai. "A Block-Adaptive Subspace Method Using Oblique Projections for Blind Separation of Convolutive Mixtures". En Advances in Neural Networks – ISNN 2005, 526–31. Berlin, Heidelberg: Springer Berlin Heidelberg, 2005. http://dx.doi.org/10.1007/11427445_86.
Texto completo
6
Dai, Qionghai y Yue Gao. "Neural Networks on Hypergraph". En Artificial Intelligence: Foundations, Theory, and Algorithms, 121–43. Singapore: Springer Nature Singapore, 2023. http://dx.doi.org/10.1007/978-981-99-0185-2_7.
Texto completoResumen
AbstractWith the development of deep learning on high-order correlations, hypergraph neural networks have received much attention in recent years. Generally, the neural networks on hypergraph can be divided into two categories, including the spectral-based methods and the spatial-based methods. For the spectral-based methods, the convolution operation is formulated in the spectral domain of graph, and we introduce the typical spectral-based methods, including hypergraph neural networks (HGNN), hypergraph convolution with attention (Hyper-Atten), and hyperbolic hypergraph neural network (HHGNN), which extend hypergraph computation to hyperbolic spaces beyond the Euclidean space. For the spatial-based methods, the convolution operation is defined in groups of spatially close vertices. We then present spatial-based hypergraph neural networks of the general hypergraph neural networks (HGNN+) and the dynamic hypergraph neural networks (DHGNN). Additionally, there are several convolution methods that attempt to reduce the hypergraph structure to the graph structure, so that the existing graph convolution methods can be directly deployed. Lastly, we analyze the association and comparison between hypergraph and graph in the two areas described above (spectral-based, spatial-based), further demonstrating the ability and advantages of hypergraph on constructing and computing higher-order correlations in the data.
7
Tang, Lihe, Weidong Yang, Qiang Gao, Rui Xu y Rongzhi Ye. "A Lightweight Verification Scheme Based on Dynamic Convolution". En Proceeding of 2021 International Conference on Wireless Communications, Networking and Applications, 778–87. Singapore: Springer Nature Singapore, 2022. http://dx.doi.org/10.1007/978-981-19-2456-9_78.
Texto completoResumen
AbstractSince Electricity Grid Engineering involves a large number of personnel in the construction process, face recognition algorithms can be used to solve the personnel management problem. The recognition devices used in Electricity Grid Engineering are often mobile, embedded, and other lightweight devices with limited hardware performance. Although a large number of existing face recognition algorithms based on deep convolutional neural networks have high recognition accuracy, they are difficult to run in mobile devices or offline environments due to high computational complexity. In order to maintain the accuracy of face recognition while reducing the complexity of face recognition networks, a lightweight face recognition network based on Dynamic Convolution is proposed. Based on MobileNetV2, this paper introduces the Dynamic Convolution operation. It proposes a Dynamic Inverted Residuals Block, which enables the lightweight neural network to combine the feature extraction and learning ability of large neural networks to improve the recognition accuracy of the model. The experiments prove that the proposed model maintains high recognition accuracy while ensuring lightweight.
8
Tran, Hoang-Dung, Neelanjana Pal, Patrick Musau, Diego Manzanas Lopez, Nathaniel Hamilton, Xiaodong Yang, Stanley Bak y Taylor T. Johnson. "Robustness Verification of Semantic Segmentation Neural Networks Using Relaxed Reachability". En Computer Aided Verification, 263–86. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-81685-8_12.
Texto completoResumen
AbstractThis paper introduces robustness verification for semantic segmentation neural networks (in short, semantic segmentation networks [SSNs]), building on and extending recent approaches for robustness verification of image classification neural networks. Despite recent progress in developing verification methods for specifications such as local adversarial robustness in deep neural networks (DNNs) in terms of scalability, precision, and applicability to different network architectures, layers, and activation functions, robustness verification of semantic segmentation has not yet been considered. We address this limitation by developing and applying new robustness analysis methods for several segmentation neural network architectures, specifically by addressing reachability analysis of up-sampling layers, such as transposed convolution and dilated convolution. We consider several definitions of robustness for segmentation, such as the percentage of pixels in the output that can be proven robust under different adversarial perturbations, and a robust variant of intersection-over-union (IoU), the typical performance evaluation measure for segmentation tasks. Our approach is based on a new relaxed reachability method, allowing users to select the percentage of a number of linear programming problems (LPs) to solve when constructing the reachable set, through a relaxation factor percentage. The approach is implemented within NNV, then applied and evaluated on segmentation datasets, such as a multi-digit variant of MNIST known as M2NIST. Thorough experiments show that by using transposed convolution for up-sampling and average-pooling for down-sampling, combined with minimizing the number of ReLU layers in the SSNs, we can obtain SSNs with not only high accuracy (IoU), but also that are more robust to adversarial attacks and amenable to verification. Additionally, using our new relaxed reachability method, we can significantly reduce the verification time for neural networks whose ReLU layers dominate the total analysis time, even in classification tasks.
9
Pattabiraman, V. y R. Maheswari. "Image to Text Processing Using Convolution Neural Networks". En Recurrent Neural Networks, 43–52. Boca Raton: CRC Press, 2022. http://dx.doi.org/10.1201/9781003307822-4.
Texto completo
10
Ma, Ruipeng, Di Wu, Tao Hu, Dong Yi, Yuqiao Zhang y Jianxia Chen. "Automatic Modulation Classification Based on One-Dimensional Convolution Feature Fusion Network". En Proceeding of 2021 International Conference on Wireless Communications, Networking and Applications, 888–99. Singapore: Springer Nature Singapore, 2022. http://dx.doi.org/10.1007/978-981-19-2456-9_90.
Texto completoResumen
AbstractDeep learning method has been gradually applied to Automatic Modulation Classification (AMC) because of its excellent performance. In this paper, a lightweight one-dimensional convolutional neural network module (OnedimCNN) is proposed. We explore the recognition effects of this module and other different neural networks on IQ features and AP features. We conclude that the two features are complementary under high and low SNR. Therefore, we use this module and probabilistic principal component analysis (PPCA) to fuse the two features, and propose a one-dimensional convolution feature fusion network (FF-Onedimcnn). Simulation results show that the overall recognition rate of this model is improved by about 10%, and compared with other automatic modulation classification (AMC) network models, our model has the lowest complexity and the highest accuracy.
Actas de conferencias sobre el tema "Convolutive Neural Networks"
1
Acharyya, Ranjan y Fredric M. Ham. "A New Approach for Blind Separation of Convolutive Mixtures". En 2007 International Joint Conference on Neural Networks. IEEE, 2007. http://dx.doi.org/10.1109/ijcnn.2007.4371278.
Texto completo
2
Wenwu Wang. "Convolutive non-negative sparse coding". En 2008 IEEE International Joint Conference on Neural Networks (IJCNN 2008 - Hong Kong). IEEE, 2008. http://dx.doi.org/10.1109/ijcnn.2008.4634325.
Texto completo
3
de Frein, Ruairi. "Learning convolutive features for storage and transmission between networked sensors". En 2015 International Joint Conference on Neural Networks (IJCNN). IEEE, 2015. http://dx.doi.org/10.1109/ijcnn.2015.7280827.
Texto completo
4
Wu, Wenyan y Liming Zhang. "A New Method of Solving Permutation Problem in Blind Source Separation for Convolutive Acoustic Signals in Frequency-domain". En 2007 International Joint Conference on Neural Networks. IEEE, 2007. http://dx.doi.org/10.1109/ijcnn.2007.4371135.
Texto completo
5
Kong, Qiuqiang, Yong Xu, Philip J. B. Jackson, Wenwu Wang y Mark D. Plumbley. "Single-Channel Signal Separation and Deconvolution with Generative Adversarial Networks". En Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/381.
Texto completoResumen
Single-channel signal separation and deconvolution aims to separate and deconvolve individual sources from a single-channel mixture. Single-channel signal separation and deconvolution is a challenging problem in which no prior knowledge of the mixing filters is available. Both individual sources and mixing filters need to be estimated. In addition, a mixture may contain non-stationary noise which is unseen in the training set. We propose a synthesizing-decomposition (S-D) approach to solve the single-channel separation and deconvolution problem. In synthesizing, a generative model for sources is built using a generative adversarial network (GAN). In decomposition, both mixing filters and sources are optimized to minimize the reconstruction error of the mixture. The proposed S-D approach achieves a peak-to-noise-ratio (PSNR) of 18.9 dB and 15.4 dB in image inpainting and completion, outperforming a baseline convolutional neural network PSNR of 15.3 dB and 12.2 dB, respectively and achieves a PSNR of 13.2 dB in source separation together with deconvolution, outperforming a convolutive non-negative matrix factorization (NMF) baseline of 10.1 dB.
6
Tong, Gan y Libo Huang. "Fast Convolution based on Winograd Minimum Filtering: Introduction and Development". En 5th International Conference on Computer Science and Information Technology (COMIT 2021). Academy and Industry Research Collaboration Center (AIRCC), 2021. http://dx.doi.org/10.5121/csit.2021.111716.
Texto completoResumen
Convolutional Neural Network (CNN) has been widely used in various fields and played an important role. Convolution operators are the fundamental component of convolutional neural networks, and it is also the most time-consuming part of network training and inference. In recent years, researchers have proposed several fast convolution algorithms including FFT and Winograd. Among them, Winograd convolution significantly reduces the multiplication operations in convolution, and it also takes up less memory space than FFT convolution. Therefore, Winograd convolution has quickly become the first choice for fast convolution implementation within a few years. At present, there is no systematic summary of the convolution algorithm. This article aims to fill this gap and provide detailed references for follow-up researchers. This article summarizes the development of Winograd convolution from the three aspects of algorithm expansion, algorithm optimization, implementation, and application, and finally makes a simple outlook on the possible future directions.
7
Xie, Chunyu, Ce Li, Baochang Zhang, Chen Chen, Jungong Han y Jianzhuang Liu. "Memory Attention Networks for Skeleton-based Action Recognition". En Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}. California: International Joint Conferences on Artificial Intelligence Organization, 2018. http://dx.doi.org/10.24963/ijcai.2018/227.
Texto completoResumen
Skeleton-based action recognition task is entangled with complex spatio-temporal variations of skeleton joints, and remains challenging for Recurrent Neural Networks (RNNs). In this work, we propose a temporal-then-spatial recalibration scheme to alleviate such complex variations, resulting in an end-to-end Memory Attention Networks (MANs) which consist of a Temporal Attention Recalibration Module (TARM) and a Spatio-Temporal Convolution Module (STCM). Specifically, the TARM is deployed in a residual learning module that employs a novel attention learning network to recalibrate the temporal attention of frames in a skeleton sequence. The STCM treats the attention calibrated skeleton joint sequences as images and leverages the Convolution Neural Networks (CNNs) to further model the spatial and temporal information of skeleton data. These two modules (TARM and STCM) seamlessly form a single network architecture that can be trained in an end-to-end fashion. MANs significantly boost the performance of skeleton-based action recognition and achieve the best results on four challenging benchmark datasets: NTU RGB+D, HDM05, SYSU-3D and UT-Kinect.
8
Lin, Luojun, Lingyu Liang, Lianwen Jin y Weijie Chen. "Attribute-Aware Convolutional Neural Networks for Facial Beauty Prediction". En Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/119.
Texto completoResumen
Facial beauty prediction (FBP) aims to develop a machine that automatically makes facial attractiveness assessment. To a large extent, the perception of facial beauty for a human is involved with the attributes of facial appearance, which provides some significant visual cues for FBP. Deep convolution neural networks (CNNs) have shown its power for FBP, but convolution filters with fixed parameters cannot take full advantage of the facial attributes for FBP. To address this problem, we propose an Attribute-aware Convolutional Neural Network (AaNet) that modulates the filters of the main network, adaptively, using parameter generators that take beauty-related attributes as extra inputs. The parameter generators update the filters in the main network in two different manners: filter tuning or filter rebirth. However, AaNet takes attributes information as prior knowledge, that is ill-suited to those datasets merely with task-oriented labels. Therefore, imitating the design of AaNet, we further propose a Pseudo Attribute-aware Convolutional Neural Network (P-AaNet) that modulates filters conditioned on global context embeddings (pseudo attributes) of input faces learnt by a lightweight pseudo attribute distiller. Extensive ablation studies show that the AaNet and P-AaNet improve the performance of FBP when compared to conventional convolution and attention scheme, which validates the effectiveness of our method.
9
Peserico, Nicola, Hangbo Yang, Xiaoxuan Ma, Shurui Li, Jonathan K. George, Puneet Gupta, Chee Wei Wong y Volker J. Sorger. "Design and Model of On-Chip Metalens for Silicon Photonics Convolutional Neural Network". En CLEO: Applications and Technology. Washington, D.C.: Optica Publishing Group, 2023. http://dx.doi.org/10.1364/cleo_at.2023.jw2a.77.
Texto completoResumen
Convolution Neural Networks are one of the most diffuse Neural Networks. Here, we present a Silicon photonic CNN chip that leverages hardware complexity by exploiting Fourier light properties to perform convolution operations, focusing on the chip- based Fourier-lens.
10
Zhu, Zulun, Jiaying Peng, Jintang Li, Liang Chen, Qi Yu y Siqiang Luo. "Spiking Graph Convolutional Networks". En Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}. California: International Joint Conferences on Artificial Intelligence Organization, 2022. http://dx.doi.org/10.24963/ijcai.2022/338.
Texto completoResumen
Graph Convolutional Networks (GCNs) achieve an impressive performance due to the remarkable representation ability in learning the graph information. However, GCNs, when implemented on a deep network, require expensive computation power, making them difficult to be deployed on battery-powered devices. In contrast, Spiking Neural Networks (SNNs), which perform a bio-fidelity inference process, offer an energy-efficient neural architecture. In this work, we propose SpikingGCN, an end-to-end framework that aims to integrate the embedding of GCNs with the biofidelity characteristics of SNNs. The original graph data are encoded into spike trains based on the incorporation of graph convolution. We further model biological information processing by utilizing a fully connected layer combined with neuron nodes. In a wide range of scenarios (e.g., citation networks, image graph classification, and recommender systems), our experimental results show that the proposed method could gain competitive performance against state-of-the-art approaches. Furthermore, we show that SpikingGCN on a neuromorphic chip can bring a clear advantage of energy efficiency into graph data analysis, which demonstrates its great potential to construct environment-friendly machine learning models.